mlcommons / modelbench

Run safety benchmarks against AI models and view detailed reports showing how well they performed.
https://mlcommons.org/ai-safety/
Apache License 2.0
62 stars 11 forks source link

Unite hugging face secrets for consistency and to fix broken daily tests #459

Open rogthefrog opened 1 month ago

rogthefrog commented 1 month ago

FAILED plugins/validation_tests/test_object_creation.py::test_all_suts_can_evaluate[gemma-9b-it-hf] - modelgauge.secret_values.MissingSecretValues: Missing the following secrets: scope='hugging_face' key='token' instructions='You can create tokens at https://huggingface.co/settings/tokens.'

https://github.com/mlcommons/modelgauge/actions/runs/10946716015/job/30393852466

rogthefrog commented 1 month ago

https://github.com/mlcommons/modelbench/pull/466

https://github.com/mlcommons/modeltune/pull/162